FreeAIRepo
Training & fine-tuning

facebookresearch/CodeGen

Reference implementation of code generation projects from Facebook AI Research. General toolkit to apply machine learning to code, from dataset creation to model training and evaluation. Comes with pr

Commercial OK · MITPython
Open on GitHub
Stars
775
Forks
144
Open issues
36
Last push
7mo ago

About CodeGen

CodeGen is a free, open-source machine learning tool by facebookresearch, written mainly in Python. Reference implementation of code generation projects from Facebook AI Research. General toolkit to apply machine learning to code, from dataset creation to model training and evaluation. Comes with pr. It has 775 GitHub stars and 144 forks, and was last updated 7mo ago. It's released under the MIT license, a standard open-source license.

License
MIT
Commercial use
Commercial OK
Language
Python
Stars
775
Last update
7mo ago
Runs on Mac
Not stated
GPU
Not stated
Paid API key
Not stated
Self-hostable
Not stated

Similar free tools

All Training & fine-tuning tools →

CodeGen FAQ

Can I use CodeGen commercially?

Yes. MIT is a permissive license: commercial use is allowed as long as you keep the license notice. This is a plain-English summary, not legal advice.

Is CodeGen free?

Yes. CodeGen is open source and free to use. It's released under the MIT license, a standard open-source license.

Does CodeGen run on a Mac?

The project doesn't say. Check its installation guide before you start.

Does CodeGen need a GPU?

The project doesn't state hardware needs. AI models generally run much faster with a GPU.

Is CodeGen still maintained?

It was last updated 7mo ago. Check recent issues on GitHub to judge how active it is.

What are alternatives to CodeGen?

Similar free, open-source tools include datasets, easy-dataset, pytorch-lightning, lmms-eval.

Related topics

code generationfacetrainingdatasetevaluationtoolkitcodegen